Data from "Modelling calibration uncertainty in networks of environmental sensors"

<p>A set of (slow motion) videos of bumblebees taken around 2020. Dataset also contains a CSV file with citizen science guesses as to the species in each, guesses by a neural network and a ground truth (from an expert).</p> <h4>Videos</h4> <p>The videos (are stored in the set of zip files, to make it </p> <p>easier to download/upload.</p> <p><br></p> <p>Videos: </p> <p> - taken using smart phones with slow motion mode.</p> <p> - codec: H.264 (High Profile).</p> <p> - 1280 × 720.</p> <p> - mp4.</p> <h4>CSV</h4> <p>The CSV file contains the following headers:</p> <p>  > video -- the filename of the video (see in zip files)</p> <p>  > person 1..person 5 -- the guesses by each individual as to the species. No entry means they didn't guess for that entry.</p> <p>  > CNN -- the guesses by the convolutional neural network*</p> <p>  > ground truth -- the guess by an expert.</p> <p>Most entries are either blank or the scientific name for a species. There is also 'whitebuff' -- which means that bee was either Bombus terrestris or one of the Bombus lucorum species, but are very often too difficult to distinguish in the field, so have been combined.</p> <p><br></p> <p>* For how these predictions were made, see Ollett, J. (2021) Bumblebee classification with convolutional neural networks<em>. Undergraduate final year dissertation, University of Sheffield.</em></p>